json: Report unterminated JSON strings as syntax errors

ext/json/json_scanner.re

@@ -262,7 +262,14 @@ std:
 		s->errcode = PHP_JSON_ERROR_UTF8;
 		return PHP_JSON_T_ERROR;
 	}
-
+	<STR_P1>EOI             {
+		if (s->limit < s->cursor) {
+			s->errcode = PHP_JSON_ERROR_SYNTAX;
+		} else {
+			s->errcode = PHP_JSON_ERROR_CTRL_CHAR;
+		}
+		return PHP_JSON_T_ERROR;
+	}
 	<STR_P1>CTRL             {
 		s->errcode = PHP_JSON_ERROR_CTRL_CHAR;
 		return PHP_JSON_T_ERROR;

ext/json/tests/gh22527.phpt

@@ -0,0 +1,31 @@
+--TEST--
+GH-22527: Unterminated JSON strings are misleadingly reported as “Control character error”
+--FILE--
+<?php
+
+var_dump(json_decode('"'));
+var_dump(json_last_error(), json_last_error_msg());
+
+var_dump(json_decode('"123'));
+var_dump(json_last_error(), json_last_error_msg());
+
+var_dump(json_decode('{"123": "'));
+var_dump(json_last_error(), json_last_error_msg());
+
+var_dump(json_decode('"' . chr(0)));
+var_dump(json_last_error(), json_last_error_msg());
+
+?>
+--EXPECT--
+NULL
+int(4)
+string(30) "Syntax error near location 1:1"
+NULL
+int(4)
+string(30) "Syntax error near location 1:1"
+NULL
+int(4)
+string(30) "Syntax error near location 1:9"
+NULL
+int(3)
+string(71) "Control character error, possibly incorrectly encoded near location 1:1"

ext/json/tests/json_last_error_msg_error_location_001.phpt

@@ -66,8 +66,8 @@ string(30) "Syntax error near location 1:1"
 
 Error at position 1:10:
 bool(false)
-int(3)
-string(72) "Control character error, possibly incorrectly encoded near location 1:10"
+int(4)
+string(31) "Syntax error near location 1:10"
 
 Error at position 1:9:
 bool(false)
@@ -118,4 +118,3 @@ Error at position 1:10:
 bool(false)
 int(3)
 string(72) "Control character error, possibly incorrectly encoded near location 1:10"
-

ext/json/tests/json_last_error_msg_error_location_002.phpt

@@ -53,51 +53,50 @@ Testing error locations with Unicode UTF-8 characters
 
 Error after Japanese characters:
 bool(false)
-int(3)
-string(72) "Control character error, possibly incorrectly encoded near location 1:12"
+int(4)
+string(31) "Syntax error near location 1:12"
 
 Error after Russian characters:
 bool(false)
-int(3)
-string(71) "Control character error, possibly incorrectly encoded near location 1:9"
+int(4)
+string(30) "Syntax error near location 1:9"
 
 Error after Chinese characters:
 bool(false)
-int(3)
-string(71) "Control character error, possibly incorrectly encoded near location 1:8"
+int(4)
+string(30) "Syntax error near location 1:8"
 
 Error after Arabic characters:
 bool(false)
-int(3)
-string(71) "Control character error, possibly incorrectly encoded near location 1:9"
+int(4)
+string(30) "Syntax error near location 1:9"
 
 Error after Emoji:
 bool(false)
-int(3)
-string(72) "Control character error, possibly incorrectly encoded near location 1:11"
+int(4)
+string(31) "Syntax error near location 1:11"
 
 Error in mixed ASCII and UTF-8:
 bool(false)
-int(3)
-string(72) "Control character error, possibly incorrectly encoded near location 1:27"
+int(4)
+string(31) "Syntax error near location 1:27"
 
 Error with UTF-8 escaped sequences:
 bool(false)
-int(3)
-string(72) "Control character error, possibly incorrectly encoded near location 1:10"
+int(4)
+string(31) "Syntax error near location 1:10"
 
 Error in object with multiple UTF-8 keys:
 bool(false)
-int(3)
-string(72) "Control character error, possibly incorrectly encoded near location 1:22"
+int(4)
+string(31) "Syntax error near location 1:22"
 
 Error in array with UTF-8 strings:
 bool(false)
-int(3)
-string(72) "Control character error, possibly incorrectly encoded near location 1:18"
+int(4)
+string(31) "Syntax error near location 1:18"
 
 Error in nested object with UTF-8:
 bool(false)
-int(3)
-string(72) "Control character error, possibly incorrectly encoded near location 1:15"
-
+int(4)
+string(31) "Syntax error near location 1:15"

ext/json/tests/json_last_error_msg_error_location_004.phpt

@@ -53,8 +53,8 @@ Testing error locations in deeply nested structures
 
 Error in deeply nested object:
 bool(false)
-int(3)
-string(72) "Control character error, possibly incorrectly encoded near location 1:31"
+int(4)
+string(31) "Syntax error near location 1:31"
 
 Error in deeply nested array:
 bool(true)
@@ -78,16 +78,15 @@ string(31) "Syntax error near location 1:21"
 
 Error in complex structure:
 bool(false)
-int(3)
-string(72) "Control character error, possibly incorrectly encoded near location 1:93"
+int(4)
+string(31) "Syntax error near location 1:93"
 
 Error in array of objects:
 bool(false)
-int(3)
-string(72) "Control character error, possibly incorrectly encoded near location 1:68"
+int(4)
+string(31) "Syntax error near location 1:68"
 
 Error in object with array values:
 bool(false)
 int(2)
 string(61) "State mismatch (invalid or malformed JSON) near location 1:82"
-

ext/json/tests/json_last_error_msg_error_location_005.phpt

@@ -53,51 +53,50 @@ Testing error locations with UTF-16 surrogate pairs and escape sequences
 
 Error after UTF-16 escaped emoji:
 bool(false)
-int(3)
-string(72) "Control character error, possibly incorrectly encoded near location 1:11"
+int(4)
+string(31) "Syntax error near location 1:11"
 
 Error after multiple UTF-16 pairs:
 bool(false)
-int(3)
-string(72) "Control character error, possibly incorrectly encoded near location 1:10"
+int(4)
+string(31) "Syntax error near location 1:10"
 
 Error with mixed UTF-8 and UTF-16:
 bool(false)
-int(3)
-string(72) "Control character error, possibly incorrectly encoded near location 1:11"
+int(4)
+string(31) "Syntax error near location 1:11"
 
 Error with UTF-16 in key:
 bool(false)
-int(3)
-string(71) "Control character error, possibly incorrectly encoded near location 1:9"
+int(4)
+string(30) "Syntax error near location 1:9"
 
 Error with multiple UTF-16 keys:
 bool(false)
-int(3)
-string(72) "Control character error, possibly incorrectly encoded near location 1:22"
+int(4)
+string(31) "Syntax error near location 1:22"
 
 Error with BMP characters:
 bool(false)
-int(3)
-string(72) "Control character error, possibly incorrectly encoded near location 1:10"
+int(4)
+string(31) "Syntax error near location 1:10"
 
 Error with supplementary plane:
 bool(false)
-int(3)
-string(72) "Control character error, possibly incorrectly encoded near location 1:11"
+int(4)
+string(31) "Syntax error near location 1:11"
 
 Error in array with UTF-16:
 bool(false)
-int(3)
-string(72) "Control character error, possibly incorrectly encoded near location 1:12"
+int(4)
+string(31) "Syntax error near location 1:12"
 
 Error in nested structure with UTF-16:
 bool(false)
-int(3)
-string(72) "Control character error, possibly incorrectly encoded near location 1:18"
+int(4)
+string(31) "Syntax error near location 1:18"
 
 Error with UTF-16 and control chars:
 bool(false)
-int(3)
-string(72) "Control character error, possibly incorrectly encoded near location 1:10"
-
+int(4)
+string(31) "Syntax error near location 1:10"

ext/json/tests/json_last_error_msg_error_location_006.phpt

@@ -107,8 +107,8 @@ string(33) "Syntax error near location 1:1011"
 
 Error with very long key:
 bool(false)
-int(3)
-string(73) "Control character error, possibly incorrectly encoded near location 1:506"
+int(4)
+string(32) "Syntax error near location 1:506"
 
 Error after empty object:
 bool(false)
@@ -149,4 +149,3 @@ Error with mixed whitespace:
 bool(false)
 int(3)
 string(71) "Control character error, possibly incorrectly encoded near location 3:2"
-

ext/json/tests/json_last_error_msg_error_location_007.phpt

@@ -118,8 +118,8 @@ string(30) "Syntax error near location 1:9"
 
 Unclosed string:
 bool(false)
-int(3)
-string(71) "Control character error, possibly incorrectly encoded near location 1:9"
+int(4)
+string(30) "Syntax error near location 1:9"
 
 Invalid escape sequence:
 bool(false)
@@ -175,4 +175,3 @@ Missing comma between object properties:
 bool(false)
 int(4)
 string(30) "Syntax error near location 1:9"
-